diff options
| author | Devajith Valaparambil Sreeramaswamy <devajith.sreeramaswamy@huawei.com> | 2023-03-08 14:30:16 -0800 |
|---|---|---|
| committer | Hanhan Wang <hanchung@google.com> | 2023-03-08 14:31:54 -0800 |
| commit | 991945f4410af9df33f0889bf3c0695fd45a28b1 (patch) | |
| tree | be4936a29e814f9035ff8438b18296f6fb7aaf83 /lldb/source/Plugins/ObjectFile/JSON/ObjectFileJSON.h | |
| parent | ac4c0ea73b11869898db2a007e3b3da2e352ecbc (diff) | |
| download | llvm-991945f4410af9df33f0889bf3c0695fd45a28b1.zip llvm-991945f4410af9df33f0889bf3c0695fd45a28b1.tar.gz llvm-991945f4410af9df33f0889bf3c0695fd45a28b1.tar.bz2 | |
[mlir][linalg] Downscale 2D convolution with unit dimensions to 1D convolution
Decompose conv_2d -> conv_1d.
This MR follows a similar approach to https://reviews.llvm.org/D112928.
This patch adds support to convert conv_2D operation with either unit height or unit width to conv_1D operation.
This is useful when 2D convolution is tiled to have a single dimension for either height or width and then can be vectorized once it is decomposed into 1D convolution.
This patch https://reviews.llvm.org/D145160 adds vector support for linalg.conv_1d operation and thereby allowing us to vectorize linalg.conv_2d operation after proper tiling.
This missing feature is reported here: https://discourse.llvm.org/t/vectorization-of-convolution-op/60458.
Reviewed By: hanchung
Differential Revision: https://reviews.llvm.org/D145162
Diffstat (limited to 'lldb/source/Plugins/ObjectFile/JSON/ObjectFileJSON.h')
0 files changed, 0 insertions, 0 deletions